MCP Risk

Directory / server

ai.bolthub/mcp

This directory entry reports an automated security scan of ai.bolthub/mcp, scanned 2026-07-28. Trust grade A rates provenance, transport, known vulnerabilities and instruction integrity; capability risk is reported separately, not folded into the grade.

registry.modelcontextprotocol.io, scanned 2026-07-28, tool surface via package-source

A 92/100 permalink

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.bolthub/mcp. 1 finding
  • Registry entry: ai.bolthub/mcp ↗
PASS Source repository is public and maintained §1.2
Active repository with a license. 5 findings
  • Repository ↗
  • Last push: 3 days ago
  • Stars: 0
  • License: MIT
  • Security policy (SECURITY.md): absent
WARN Published package is consistent and attested §1.3
Minor integrity gaps: package is only 21 days old. 6 findings
  • Package: @bolthub/mcp@0.7.2 ↗
  • Ecosystem: npm
  • Age: 21 days
  • Weekly downloads: 606
  • Repo field matches source repo: true
  • Build-provenance attestation: present
PASS Tool surface is inspectable and proportionate §2.1–§2.4
Package source scanned. Capabilities detected: process-execution, filesystem, network-egress. Reported as capability risk (§2.4); whether each is essential to the server's stated purpose is §2.3 and remains a manual judgement. 6 findings
  • process-execution (child process execution): dist/index.js
  • process-execution (dynamic code evaluation): dist/index.js
  • filesystem (filesystem write/delete): dist/index.js
  • filesystem (fs module import): dist/index.js
  • network-egress (outbound network calls): dist/index.js
  • Detected capabilities: process-execution, filesystem, network-egress
INFO Transport & authentication §3

Local (stdio) server: runs with host-process privileges by design. Transport checks apply to remote servers; scrutiny shifts to §1/§2.
PASS No known vulnerabilities (OSV.dev) §4.1

No advisories on record for @bolthub/mcp @0.7.2 (npm).
PASS Server-supplied instructions free of poisoning indicators §5.1–§5.4

No poisoning indicators found across 98 server-supplied text item(s).

Score history

DateGradeScore
2026-07-28A92/100
2026-07-27A92/100
2026-07-27A92/100
2026-07-27A92/100
2026-07-26A92/100
2026-07-26A92/100
2026-07-26A92/100
2026-07-26F41/100
2026-07-25F39/100
2026-07-25F39/100
2026-07-25F39/100
2026-07-25F39/100
2026-07-24F39/100
2026-07-24F39/100
2026-07-24F41/100
2026-07-12D50/100
What this grade covers
  • Provenance & supply-chain integrity (§1)
  • Tool surface & capability risk (§2)
  • Transport & authentication (§3)
  • Known CVEs via OSV.dev (§4)
  • Instruction/tool poisoning patterns (§5)

Limitations: pattern-based only (no semantic injection detection), static npm analysis (live server instructions not retrieved for package-only scans), single-server scope (no cross-server toxic flow analysis). See the full policy.

Methodology: MCP Server Security Policy. Unfamiliar term? See the glossary.